Title :
Handwritten isolated word recognition: an approach based on Mutual Information for feature set validation
Author :
Freitas, Cinthia O A ; Bortolozzi, Flávio ; Sabourin, Robert
Author_Institution :
1-Pontificia Univ. Catolica do Parana, Curitiba, Brazil
fDate :
6/23/1905 12:00:00 AM
Abstract :
The paper presents the application of the Mutual Information criterion (T.M. Cover and J.A. Thomas, 1991) to validate feature sets extracted from handwritten words in Brazilian legal amounts. The lexicon includes a subset of short words without ascenders/descenders and subsets of words with the same prefix or suffix. These particularities of the Brazilian lexicon show that it is necessary to improve the perpetual feature set with complementary geometric features, and also modeling the prefix and suffix of the words. Finally, the experiments show the viability of our approach
Keywords :
feature extraction; handwritten character recognition; information theory; law administration; speech recognition; word processing; Brazilian legal amounts; Brazilian lexicon; Mutual Information criterion; complementary geometric features; feature set validation; handwritten isolated word recognition; handwritten words; perpetual feature set; prefix; short words; suffix; Data mining; Entropy; Feature extraction; Handwriting recognition; Hidden Markov models; Law; Legal factors; Mutual information; Random variables; Solid modeling;
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953873
